UM
Residential Collegefalse
Status已發表Published
Multi-mode dynamic residual graph convolution network for traffic flow prediction
Huang, Xiaohui1; Ye, Yuming1; Ding, Weihua1; Yang, Xiaofei2; Xiong, Liyan1
2022-09-01
Source PublicationInformation Sciences
ISSN0020-0255
Volume609Pages:548-564
Abstract

Urban traffic congestion is not only an important cause of traffic accidents, but also a major hinder to urban development. By learning the historical traffic flow data, we can forecast the traffic flow of some regions in the future, which is of great significance to urban road planning, traffic management, traffic control and many more. However, due to the complex topology of traffic network and the diversity of influencing factors to traffic flow, the traffic modes are usually complicated and volatile, which makes traffic flow prediction very difficult. In this paper, we propose a new graph convolution neural network, namely Multi-mode Dynamic Residual Graph Convolution Network (MDRGCN), to capture the dynamic impact of different factors on traffic flow in a road network simultaneously. Firstly, we design a multi-mode dynamic graph convolution module (MDGCN), which is employed to capture the impact of different traffic modes by learning two types of relationship matrices. Then, we design a multi-mode dynamic graph convolution gated recurrent unit (MDGRU) to realize the combination of spatial and temporal dependences. Finally, we use a dynamic residual module (DRM) to integrate the orginal traffic data and the spatio-temporal features extracted by the MDGRU module to forecast the future traffic flow. Experimental reulsts conducted on the NYCTaxi and NYCBike datasets validate that the MDRGCN model performs better than the other eight baselines.

KeywordGraph Convolution Network Multi-mode Fusion Spatio-temporal Data Traffic Flow Prediction
DOI10.1016/j.ins.2022.07.008
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000848150900009
Scopus ID2-s2.0-85134885700
Fulltext Access
Citation statistics
Cited Times [WOS]:4   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Affiliation1.Department of Information Engineering, East China Jiaotong University, Jiangxi, China
2.Faculty of Science and Technology, University of Macau, Macau, China
Recommended Citation
GB/T 7714
Huang, Xiaohui,Ye, Yuming,Ding, Weihua,et al. Multi-mode dynamic residual graph convolution network for traffic flow prediction[J]. Information Sciences,2022,609:548-564.
APA Huang, Xiaohui,Ye, Yuming,Ding, Weihua,Yang, Xiaofei,&Xiong, Liyan.(2022).Multi-mode dynamic residual graph convolution network for traffic flow prediction.Information Sciences,609,548-564.
MLA Huang, Xiaohui,et al."Multi-mode dynamic residual graph convolution network for traffic flow prediction".Information Sciences 609(2022):548-564.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang, Xiaohui]'s Articles
[Ye, Yuming]'s Articles
[Ding, Weihua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang, Xiaohui]'s Articles
[Ye, Yuming]'s Articles
[Ding, Weihua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang, Xiaohui]'s Articles
[Ye, Yuming]'s Articles
[Ding, Weihua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.